The analysis of WtM credit used baseline and final follow-up Farming Practices Survey (FPS) data to summarize beneficiary and loan characteristics, as well as to estimate the impact of MCA credit on the key outcomes of investment, production, sales, and income. To construct these estimates, the evaluator used regression modeling to compare farmers who did and did not receive MCA credit. The evaluator supplemented the quantitative analysis with qualitative information on program implementation and intended results based on interviews with MCA staff, RFF personnel, lending organizations participating in the program, and representatives from other donor organizations in Armenia.
Kind of Data
Sample survey data [ssd]
Unit of Analysis
The units of analysis are individuals and families/households.
Edited clean data for internal use only
Agriculture and Irrigation
Rural areas in the 10 Armenian marzes excepting Yerevan.
Unit of Analysis
The units of analysis are individuals and families/households.
The survey covered farming households in rural communities that were included in the evaluation sample for the Water-to-Market impact evaluation. It is not a representative sample of those who received or were eligible for credit.
Producers and sponsors
Authoring entity/Primary investigators
Mathematica Policy Research
Millennium Challenge Corporation
The evaluation design for the WtM activities dictated the sampling frame and approach to the FPS. The FPS focused on constructing a sample appropriate for rigorously assessing impacts of the farmer training component of WtM. The credit evaluation used the same data, but for the credit evaluation it was a sample of convenience rather than representative of any broader population.
The target was to complete interviews with approximately 25 farmers in each of 189 village clusters that was selected to be in the evaluation of WtM training. Village clusters consist of up to 4 small, neighboring villages, and the 189 selected village clusters cover 211 villages.
The baseline survey did not randomly sample respondents from the village clusters. The field team identified respondents for the FPS by working with village mayors to identify farmers who were likely to participate in WtM training so that a high proportion of farmers who were interviewed would have participated in training. The criteria were designed to align with the characteristics of farmers participating in ACDI's training programs, most notably, being actively engaged in farming, having modest farm area, living in the community for several years, and being between 25 and 70 years old.
AREG updated the sample list with the assistance of village mayors and marz officials, either at the marz offices or in the village itself. AREG and mayors targeted the households of farmers who were actively engaged in farming and had lived in the community for several years. Ultimately, a total of 4,715 farming households were interviewed for FPS1 in relevant communities. These same households were targeted for FPS3, which acheived a response rate of 75%.
Deviations from the Sample Design
Three villages that were originally sampled for the FPS were not surveyed at final follow-up. Two villages that were surveyed at baseline were not surveyed at final follow-up because they were found to have almost no active farmers. A third village was not accessible for the baseline FPS due to heavy snow. The rest of the villages in these WUAs were surveyed at baseline and final follow-up according to the sample design.
For FPS3, MCA-Armenia also added the objective of surveying recipients of MCA credit. As a result, the FPS3 was administered to 33 new farmers who had not been interviewed in FPS1 and had received MCA credit.
The FPS3 was administered to 3,547 households, 75 percent of households that participated in FPS1.
Nonresponse weights were constructed to account for households that responded to FPS1 and did not respond to FPS3. The nonresponse weights were computed by first calculating the propensity of a household's nonresponse in the FPS3. The second step in creating nonresponse weights was to use the predicted values from the response propensity models to create weighting cells. Within each research group (treatment and control), five weighting cells were created that were determined by the size of the predicted likelihood that the household responded to the survey. This resulted in a total of 10 (5 x 2) weighting cells. The same nonresponse weight was assigned within each of these 10 cells.
The third step was to create the nonresponse weight for each cell. The nonresponse weight was calculated by dividing the total number of households in each cell by the total number of households that responded to the survey in each cell. Finally, the weights were rescaled such that the sum of weights for the treatment group and the sum of weights for the control group each equal the original sample size of 4,715. Additional details of the calculations of nonresponse weights are provided in Appendix A of the Water-to-Market Evaluation report, which is provided as a resource document.
Dates of Data Collection (YYYY/MM/DD)
The thirty interviewers were divided into 5 groups, each led by a field coordinator. The Administrative Assistant to the Team Leader at AREG supervised the fieldwork and observed several interviews in the field. The field coordinators reported at least weekly to the Team Leader, Senior Researcher, and Administrative Assistant to the Team Leader at AREG. The role of the Team Leader was to manage all aspects of the pre-test, sample verification, and data collection. The Team Leader also communicated the progress of the fieldwork with MCA-Armenia and MPR. The role of the Senior Researcher was to provide guidance on survey implementation, pre-tests, and revisions to the FPS3. The Senior Researcher was also responsible for interviewer training and developing the data processing and quality control approaches. The Administrative Assistant to the Team Leader was responsible for selecting the interviewers, scheduling interviewers, and supervising fieldwork coordinators, the sample verification team, and the quality control team.
Type of Research Instrument
There is one questionnaire for the Farming Practices Survey 3 (FPS3). The FPS3 is based on the questionnaire used in FPS1 and the Integrated Survey of Living Standards (ISLS) implemented annually by the National Statistical Service of Armenia (NSS). The FPS3 is published in Armenian and English. It is intended to be administered to the person in the household with the most knowledge of farming activities on the household's land holdings.
The FPS3 was designed with guidance from MCA-Armenia, MCC, and Mathematica. Relative to FPS1, FPS3 has some minor changes in structure and an additional section on agricultural credit. In addition to questions regarding agricultural credit, the FPS3 asks about various demographic and socioeconomic characteristics for each member of the household, including sex, age, relationship, education level, and occupation. At the household level, the FPS3 asks the respondent about agricultural trainings, land holdings, agricultural practices, production of major crops, agricultural sales and revenues, income, and expenses.
Jen Finance, Engineering, and Management Consult Ltd
AREG Scientific Cultural Youth Association Non-Governmental Organization
After interviewers completed each questionnaire, the interviewers reviewed the questionnaire entries and submitted them to the field coordinator for cross-editing. During data entry in SPSS, mistakes were corrected using visual and program control. In the analysis phase, subsequent edits were made to logically impute data where appropriate.
"Millennium Challenge Corporation, Farming Practices Survey 2006-07 (FPS1) and Farming Practices Survey 2010-11 (FPS3), Version 2.0 of the public use dataset (August 2012). www.mcc.gov"